fix(mcp): keep the session on tool-call protocol errors and report quarantine truthfully

2026-09-21 00:23:52 +08:00 · 2026-09-01 22:52:00 +00:00
38 changed files with 284 additions and 570 deletions
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,6 +1,3 @@
-# Built viewer bundles are generated output, not hand-edited source.
-exclude: ^strix/interface/viewer/static/assets/
-
 repos:
  # Ruff for fast linting and formatting
  - repo: https://github.com/astral-sh/ruff-pre-commit
@@ -12,18 +9,21 @@ repos:
      - id: ruff-format
        name: ruff-format

-  # MyPy for static type checking. Runs the project's own mypy from the uv
-  # environment (`make dev-install`) so it sees the same dependencies and
-  # stubs as `make check-all`.
-  - repo: local
+  # MyPy for static type checking
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.17.1
    hooks:
      - id: mypy
-        name: mypy
-        entry: uv run mypy
-        language: system
-        types_or: [python, pyi]
-        files: ^(strix|tests)/
-        require_serial: true
+        additional_dependencies: [
+          types-requests,
+          types-python-dateutil,
+          pydantic,
+          fastapi,
+          pytest,
+          hatchling,
+          "openai-agents[litellm]>=0.19.0,<0.20",
+        ]
+        args: [--install-types, --non-interactive]

  # Built-in hooks for basic file checks
  - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -62,6 +62,5 @@ ci:
  autoupdate_branch: ""
  autoupdate_commit_msg: "[pre-commit.ci] pre-commit autoupdate"
  autoupdate_schedule: weekly
-  # pre-commit.ci cannot run `language: system` hooks; mypy runs via `make check-all`.
-  skip: [mypy]
+  skip: []
  submodules: false
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -28,7 +28,7 @@ Target-specific workflows built on the same engine:
 - **Open-source CLI (self-hosted):** free, fully local, BYO LLM key, needs Docker. Best for local dev loops, air-gapped/offline, and full control.
  ```bash
  curl -sSL https://strix.ai/install | bash        # install
-  export STRIX_LLM="openrouter/z-ai/glm-5.3"        # any LiteLLM model id
+  export STRIX_LLM="openai/gpt-5.4"                 # any LiteLLM model id
  export LLM_API_KEY="<key>"
  strix -n -t ./ --scan-mode quick --max-budget 10  # headless scan; always use -n
  ```
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -31,7 +31,7 @@ Thank you for your interest in contributing to Strix! This guide will help you g

 3. **Configure your LLM provider**
   ```bash
-   export STRIX_LLM="openrouter/z-ai/glm-5.3"
+   export STRIX_LLM="openai/gpt-5.4"
   export LLM_API_KEY="your-api-key"
   ```

--- a/README.md
+++ b/README.md
@@ -82,7 +82,7 @@ Strix are autonomous AI penetration testing agents that act just like real hacke
 curl -sSL https://strix.ai/install | bash

 # Configure your AI provider
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"

 # Run your first security assessment
@@ -294,7 +294,7 @@ jobs:
 ### Configuration

 ```bash
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"

 # Optional
@@ -448,12 +448,9 @@ Each server's tools are namespaced by `name` (for example `local_fs_read_file`).

 **Recommended models for best results:**

- [Z.ai GLM-5.3 on OpenRouter](https://openrouter.ai/z-ai/glm-5.3) - `openrouter/z-ai/glm-5.3` (the default pick)
 - [OpenAI GPT-5.4](https://openai.com/api/) - `openai/gpt-5.4`
 - [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) - `anthropic/claude-sonnet-4-6`
 - [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) - `vertex_ai/gemini-3-pro-preview`
- [DeepSeek V4 Pro](https://platform.deepseek.com) - `deepseek/deepseek-v4-pro`
- [Moonshot Kimi K3](https://platform.kimi.ai) - `moonshot/kimi-k3`

 See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models.

--- a/docs/advanced/configuration.mdx
+++ b/docs/advanced/configuration.mdx
@@ -8,7 +8,7 @@ Configure Strix using environment variables or a config file.
 ## LLM Configuration

 <ParamField path="STRIX_LLM" type="string" required>
-  Model name in LiteLLM format (e.g., `openrouter/z-ai/glm-5.3`, `openai/gpt-5.4`).
+  Model name in LiteLLM format (e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4-6`).
 </ParamField>

 <ParamField path="LLM_API_KEY" type="string">
@@ -145,7 +145,7 @@ strix --target ./app --config /path/to/config.json
 ```json
 {
  "env": {
-    "STRIX_LLM": "openrouter/z-ai/glm-5.3",
+    "STRIX_LLM": "openai/gpt-5.4",
    "LLM_API_KEY": "sk-...",
    "STRIX_REASONING_EFFORT": "high"
  }
@@ -156,7 +156,7 @@ strix --target ./app --config /path/to/config.json

 ```bash
 # Required
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="sk-..."

 # Optional: Enable web search
--- a/docs/contributing.mdx
+++ b/docs/contributing.mdx
@@ -33,7 +33,7 @@ description: "Contribute to Strix development"
  </Step>
  <Step title="Configure LLM">
    ```bash
-    export STRIX_LLM="openrouter/z-ai/glm-5.3"
+    export STRIX_LLM="openai/gpt-5.4"
    export LLM_API_KEY="your-api-key"
    ```
  </Step>
--- a/docs/index.mdx
+++ b/docs/index.mdx
@@ -78,7 +78,7 @@ Strix uses a graph of specialized agents for comprehensive security testing:
 curl -sSL https://strix.ai/install | bash

 # Configure
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"

 # Scan
--- a/docs/integrations/github-actions.mdx
+++ b/docs/integrations/github-actions.mdx
@@ -37,7 +37,7 @@ Add these secrets to your repository:

 | Secret | Description |
 |--------|-------------|
-| `STRIX_LLM` | Model name (e.g., `openrouter/z-ai/glm-5.3`) |
+| `STRIX_LLM` | Model name (e.g., `openai/gpt-5.4`) |
 | `LLM_API_KEY` | API key for your LLM provider |

 ## Exit Codes
--- a/docs/llm-providers/novita.mdx
+++ b/docs/llm-providers/novita.mdx
@@ -17,9 +17,6 @@ export LLM_API_BASE="https://api.novita.ai/openai"

 | Model | Configuration |
 |-------|---------------|
-| GLM-5.3 | `openai/zai-org/glm-5.3` |
-| Kimi K3 | `openai/moonshotai/kimi-k3` |
-| DeepSeek V4 Pro | `openai/deepseek/deepseek-v4-pro` |
 | Kimi K2.5 | `openai/moonshotai/kimi-k2.5` |
 | GLM-5 | `openai/zai-org/glm-5` |
 | MiniMax M2.5 | `openai/minimax/minimax-m2.5` |
--- a/docs/llm-providers/openrouter.mdx
+++ b/docs/llm-providers/openrouter.mdx
@@ -8,7 +8,7 @@ description: "Configure Strix with models via OpenRouter"
 ## Setup

 ```bash
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openrouter/openai/gpt-5.4"
 export LLM_API_KEY="sk-or-..."
 ```

@@ -18,12 +18,9 @@ Access any model on OpenRouter using the format `openrouter/<provider>/<model>`:

 | Model | Configuration |
 |-------|---------------|
-| GLM-5.3 (default) | `openrouter/z-ai/glm-5.3` |
 | GPT-5.4 | `openrouter/openai/gpt-5.4` |
 | Claude Sonnet 4.6 | `openrouter/anthropic/claude-sonnet-4.6` |
 | Gemini 3 Pro | `openrouter/google/gemini-3-pro-preview` |
-| DeepSeek V4 Pro | `openrouter/deepseek/deepseek-v4-pro` |
-| Kimi K3 | `openrouter/moonshotai/kimi-k3` |
 | GLM-4.7 | `openrouter/z-ai/glm-4.7` |

 ## Get API Key
--- a/docs/llm-providers/overview.mdx
+++ b/docs/llm-providers/overview.mdx
@@ -9,17 +9,14 @@ Strix uses [LiteLLM](https://docs.litellm.ai/docs/providers) for model compatibi

 Set your model and API key:

-| Model                | Provider          | Configuration                    |
-| -------------------- | ----------------- | -------------------------------- |
-| GLM-5.3 (default)    | Z.ai (OpenRouter) | `openrouter/z-ai/glm-5.3`        |
-| GPT-5.4              | OpenAI            | `openai/gpt-5.4`                 |
-| Claude Sonnet 4.6    | Anthropic         | `anthropic/claude-sonnet-4-6`    |
-| Gemini 3 Pro         | Google Vertex     | `vertex_ai/gemini-3-pro-preview` |
-| DeepSeek V4 Pro      | DeepSeek          | `deepseek/deepseek-v4-pro`       |
-| Kimi K3              | Moonshot          | `moonshot/kimi-k3`               |
+| Model             | Provider      | Configuration                    |
+| ----------------- | ------------- | -------------------------------- |
+| GPT-5.4           | OpenAI        | `openai/gpt-5.4`                 |
+| Claude Sonnet 4.6 | Anthropic     | `anthropic/claude-sonnet-4-6`    |
+| Gemini 3 Pro      | Google Vertex | `vertex_ai/gemini-3-pro-preview` |

 ```bash
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"
 ```

@@ -65,7 +62,6 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
 Use LiteLLM's `provider/model-name` format:

 ```
-openrouter/z-ai/glm-5.3
 openai/gpt-5.4
 anthropic/claude-sonnet-4-6
 vertex_ai/gemini-3-pro-preview
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -28,12 +28,12 @@ description: "Install Strix and run your first security scan"
 Set your LLM provider:

 ```bash
-export STRIX_LLM="openrouter/z-ai/glm-5.3"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-api-key"
 ```

 <Tip>
-For best results, use `openrouter/z-ai/glm-5.3` (the default pick), `openai/gpt-5.4`, `anthropic/claude-opus-4-6`, or `openai/gpt-5.2`.
+For best results, use `openai/gpt-5.4`, `anthropic/claude-opus-4-6`, or `openai/gpt-5.2`.
 </Tip>

 ## Run Your First Scan
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -250,7 +250,6 @@ ignore = [
 # Stdlib HTTP handler overrides (do_GET/do_POST) and lazy imports that avoid a
 # circular dependency with strix.telemetry / strix.interface.viewer.report_pdf.
 "strix/interface/viewer/server.py" = ["N802", "PLC0415"]
-"strix/interface/cloud/payment_proxy.py" = ["N802"]
 # Lazy telemetry import to avoid importing PostHog before the viewer starts.
 "strix/interface/viewer/cli.py" = ["PLC0415"]
 # Lazy imports inside functions to avoid circular dependency with
@@ -414,8 +413,6 @@ known_third_party = ["pydantic", "litellm"]
 # ============================================================================

 [tool.bandit]
-# Tests are covered by ruff's flake8-bandit rules (see per-file-ignores above),
-# which is where fixture tokens and loopback URL opens are already waived.
-exclude_dirs = ["docs", "build", "dist", "tests"]
+exclude_dirs = ["docs", "build", "dist"]
 skips = ["B101", "B601", "B404", "B603", "B607"]  # Skip assert, shell injection, subprocess import and partial path checks
 severity = "medium"
--- a/strix/config/codex.py
+++ b/strix/config/codex.py
@@ -183,7 +183,7 @@ def build_authorize_url(challenge: str, state: str) -> str:
        "code_challenge": challenge,
        "code_challenge_method": "S256",
        "state": state,
-        "id_token_add_organizations": "true",  # nosec B105 - boolean flag, not a secret
+        "id_token_add_organizations": "true",
        "codex_cli_simplified_flow": "true",
        "originator": ORIGINATOR,
    }
--- a/strix/config/models.py
+++ b/strix/config/models.py
@@ -562,8 +562,6 @@ DEFAULT_MODEL_RETRY = ModelRetrySettings(
 )

 RECOMMENDED_MODEL_NAMES = (
-    "zai/glm-5.3",
-    "zai/glm-5.3-flash",
    "openai/gpt-5.6-sol",
    "openai/gpt-5.6-terra",
    "openai/gpt-5.6-luna",
@@ -572,7 +570,6 @@ RECOMMENDED_MODEL_NAMES = (
    "openai/gpt-5.5",
    "openai/gpt-5.4",
    "openai/gpt-5.3-codex",
-    "anthropic/claude-fable-5-1",
    "anthropic/claude-fable-5",
    "anthropic/claude-opus-5",
    "anthropic/claude-opus-4-8",
@@ -580,8 +577,6 @@ RECOMMENDED_MODEL_NAMES = (
    "anthropic/claude-sonnet-4-6",
    "vertex_ai/gemini-3.1-pro-preview",
    "gemini/gemini-3.1-pro-preview",
-    "vertex_ai/gemini-3.7-flash",
-    "gemini/gemini-3.7-flash",
    "gemini/gemini-3.6-flash",
    "deepseek/deepseek-v4-pro",
    "deepseek/deepseek-v4-flash",
@@ -603,7 +598,6 @@ FRONTIER_MODEL_FAMILIES = (
    (("deepseek",), ("deepseek-v4", "deepseek-r1", "deepseek-reasoner")),
    (("alibaba", "dashscope", "qwen"), ("qwen3.8", "qwen3.7", "qwen3-max")),
    (("moonshot", "moonshotai", "kimi"), ("kimi-k3", "kimi-k2.7", "kimi-k2.6")),
-    (("zai", "z-ai", "zai-org", "zhipuai"), ("glm-5.3", "glm-5.2")),
 )


--- a/strix/core/runner.py
+++ b/strix/core/runner.py
@@ -428,7 +428,6 @@ async def run_strix_scan(
                        }
                        for summary in mcp_registry.summaries()
                    ]
-
                    # Feed a non-secret connection roster (name / provider /
                    # tool_count / dead) to two consumers: once now (all
                    # currently healthy) and again whenever a connection later
--- a/strix/interface/cloud/init.py
+++ b/strix/interface/cloud/init.py
@@ -14,7 +14,7 @@ import sys
 from rich.console import Console
 from rich.markup import escape

-from strix.interface.cloud import http
+import strix.interface.cloud.http as http  # noqa: PLR0402
 from strix.interface.cloud.render import json_mode
 from strix.interface.cloud.runner import resolve, run
 from strix.interface.cloud.session import run_session
--- a/strix/interface/environment.py
+++ b/strix/interface/environment.py
@@ -70,7 +70,7 @@ def validate_environment() -> None:
                error_text.append("• ", style="white")
                error_text.append("STRIX_LLM", style="bold cyan")
                error_text.append(
-                    " - Model name to use (e.g., 'openrouter/z-ai/glm-5.3' or "
+                    " - Model name to use (e.g., 'openai/gpt-5.4' or "
                    "'anthropic/claude-opus-4-7')\n",
                    style="white",
                )
@@ -102,7 +102,7 @@ def validate_environment() -> None:
                    )

        error_text.append("\nExample setup:\n", style="white")
-        error_text.append("export STRIX_LLM='openrouter/z-ai/glm-5.3'\n", style="dim white")
+        error_text.append("export STRIX_LLM='openai/gpt-5.4'\n", style="dim white")

        if missing_optional_vars:
            for var in missing_optional_vars:
--- a/strix/interface/main.py
+++ b/strix/interface/main.py
@@ -391,10 +391,13 @@ def _print_model_connection_error(exc: BaseException, model_name: str) -> None:
 def _bootstrap_scan(args: argparse.Namespace) -> None:
    """Warm up the model and prepare the run for a non-interactive scan.

-    Interactive launches skip this: the model preflight and run preparation
-    happen inside the TUI so the interface paints immediately instead of
-    waiting on a model round trip.
+    Interactive launches only validate the environment here; the model
+    preflight and run preparation happen inside the TUI so the interface
+    paints immediately instead of waiting on a model round trip.
    """
+    validate_environment()
+    if not args.non_interactive:
+        return
    try:
        asyncio.run(warm_up_llm(show_model_warning=True))
    except ModelConnectionError as exc:
@@ -464,9 +467,10 @@ def main() -> None:

    check_docker_installed()
    pull_docker_image()
-    validate_environment()

-    if args.non_interactive:
+    # In setup mode the TUI collects the target, then runs prepare_run(),
+    # warm-up, and telemetry itself once the user starts the scan.
+    if not args.needs_setup:
        _bootstrap_scan(args)

    from strix.report.state import get_global_report_state
@@ -507,7 +511,6 @@ def main() -> None:

    if not args.run_name:
        # Setup mode where the user quit before starting a scan: nothing ran.
-        notify_update(Console())
        return

    results_path = run_dir_for(args.run_name)
--- a/strix/interface/tui/backend/controller.py
+++ b/strix/interface/tui/backend/controller.py
@@ -36,8 +36,7 @@ if TYPE_CHECKING:
 _STOPPABLE_AGENT_STATUSES = frozenset({"running", "waiting", "budget_paused"})

 ChangeCallback = Callable[[], None]
-StartCallback = Callable[[], Awaitable[None]]
-VerifyCallback = Callable[[], Awaitable[None]]
+StartCallback = Callable[[bool], Awaitable[None]]
 QuitCallback = Callable[[], Awaitable[None]]


@@ -52,7 +51,6 @@ class TuiController:
        coordinator: Any = None,
        report_state: ReportState | None = None,
        on_start: StartCallback | None = None,
-        on_verify: VerifyCallback | None = None,
        on_quit: QuitCallback | None = None,
        on_change: ChangeCallback | None = None,
    ) -> None:
@@ -101,6 +99,7 @@ class TuiController:
        # A target-less launch enters the live view and asks there before
        # anything is prepared; this holds the directory awaiting that answer.
        self.pending_workspace_mount: str | None = None
+        self._pending_verify = True
        self.messages: list[dict[str, str]] = []
        self._next_message_id = 1
        self.error: str | None = None
@@ -113,7 +112,6 @@ class TuiController:
        self.viewer_url: str | None = None
        self._viewer_httpd: Any = None
        self._on_start = on_start
-        self._on_verify = on_verify
        self._on_quit = on_quit
        self._on_change = on_change

@@ -330,6 +328,12 @@ class TuiController:
    async def _start(self, payload: dict[str, Any]) -> dict[str, Any]:
        if self.scan_started or self._start_in_progress:
            raise RuntimeError("Scan is already starting or running")
+        # A bare prompt launches optimistically, like a coding agent: it skips
+        # the network model preflight and surfaces any model error live. A named
+        # target keeps the preflight so a real scan does not commit blind.
+        verify = payload.get("verify", True)
+        if not isinstance(verify, bool):
+            raise TypeError("verify must be a boolean")
        # Launching with no target mounts the working directory, so it requires
        # the user's explicit confirmation rather than happening silently.
        mount_working_dir = payload.get("mount_working_dir", False)
@@ -340,44 +344,27 @@ class TuiController:
            raise ValueError("No model configured. Set STRIX_LLM first.")
        if self._on_start is None:
            raise RuntimeError("Scan start is unavailable")
-        if not self.targets and not mount_working_dir:
-            raise ValueError("No target set. Add a target first.")
-        # The model check runs while still on the start screen, for a bare
-        # prompt as much as for a named target, so a failure lands in the setup
-        # log where the user can fix it and retry rather than in a dead run.
-        await self._verify_model()
        if not self.targets:
+            if not mount_working_dir:
+                raise ValueError("No target set. Add a target first.")
            # Mounting the working directory needs the user's confirmation, and
            # that is asked in the live view. Enter it now and prepare nothing
            # until the answer arrives, so declining leaves no run behind.
            self.pending_workspace_mount = str(Path.cwd())
+            self._pending_verify = verify
            self.setup_mode = False
            self.scan_started = True
            self.scan_state = "preparing"
            return {"started": True}
-        await self._begin_scan()
+        await self._begin_scan(verify)
        return {"started": True}

-    async def _verify_model(self) -> None:
-        if self._on_verify is None:
-            return
-        self._start_in_progress = True
-        try:
-            await self._on_verify()
-        finally:
-            self._start_in_progress = False
-
-    async def _begin_scan(self) -> None:
+    async def _begin_scan(self, verify: bool) -> None:
        if self._on_start is None:
            raise RuntimeError("Scan start is unavailable")
        self._start_in_progress = True
        try:
-            await self._on_start()
-        except Exception as exc:
-            if not self.setup_mode:
-                # The live view is already up, so the failure has to show there.
-                self.fail_preparation(str(exc))
-            raise
+            await self._on_start(verify)
        finally:
            self._start_in_progress = False
        self.setup_mode = False
@@ -397,7 +384,7 @@ class TuiController:
        # the whole of the input either way; the working directory is only an
        # extra the agent may look at, so the run goes ahead without one.
        self.workspace_mount = mount if approved else None
-        await self._begin_scan()
+        await self._begin_scan(self._pending_verify)
        return {"approved": approved}

    async def _send_message(self, payload: dict[str, Any]) -> dict[str, Any]:
--- a/strix/interface/tui/internal/app/setup.go
+++ b/strix/interface/tui/internal/app/setup.go
@@ -45,20 +45,23 @@ func (m *Model) submitSetupPrompt(value string) (tea.Model, tea.Cmd) {
 	if len(fields) > targets {
 		commands = append(commands, send(m.client, "setup.set_instruction", map[string]any{"instruction": value}))
 	}
-	// The backend verifies the model connection before either kind of launch
-	// and reports on it through the setup log. A bare prompt mounts the working
-	// directory - the backend asks about that from the live view, so the prompt
-	// is held here in case it is declined.
-	payload := map[string]any{}
-	if targets == 0 && len(m.snapshot.Targets) == 0 {
+	// With a target, verify the model connection before the scan commits to it.
+	// A bare prompt launches optimistically, like a coding agent, and mounts the
+	// working directory - the backend asks about that from the live view, so the
+	// prompt is held here in case it is declined.
+	verify := targets > 0 || len(m.snapshot.Targets) > 0
+	payload := map[string]any{"verify": verify}
+	if verify {
+		m.setupMsg("Verifying model connection...", render.Col(amber))
+	} else {
 		m.pendingPrompt = value
 		payload["mount_working_dir"] = true
 	}
 	commands = append(commands, send(m.client, "setup.start", payload))
 	// Ordered, not batched: setup.start leaves setup mode, so it must be the
-	// last command to reach the backend. Batched sends race, and if setup.start
-	// wins the target and instruction commands land after the guard closes and
-	// fail with a red error.
+	// last command to reach the backend. Batched sends race, and once the
+	// preflight is skipped setup.start wins, making the target and instruction
+	// commands land after the guard closes and fail with a red error.
 	return *m, tea.Sequence(commands...)
 }

--- a/strix/interface/tui/internal/app/setup_prompt_test.go
+++ b/strix/interface/tui/internal/app/setup_prompt_test.go
@@ -94,6 +94,25 @@ func commandTypes(envelopes []protocol.Envelope) []string {
 	return types
 }

+// startVerify returns the verify flag on the setup.start command, and whether
+// a setup.start command was present at all.
+func startVerify(t *testing.T, envelopes []protocol.Envelope) (verify, found bool) {
+	t.Helper()
+	for _, envelope := range envelopes {
+		if envelope.Type != "setup.start" {
+			continue
+		}
+		var payload struct {
+			Verify bool `json:"verify"`
+		}
+		if err := json.Unmarshal(envelope.Payload, &payload); err != nil {
+			t.Fatal(err)
+		}
+		return payload.Verify, true
+	}
+	return false, false
+}
+
 func contains(values []string, want string) bool {
 	for _, value := range values {
 		if value == want {
@@ -141,6 +160,10 @@ func TestSetupPromptWithoutTargetLaunchesAndRequestsMount(t *testing.T) {
 	if mount, found := startPayloadFlag(t, envelopes, "mount_working_dir"); !found || !mount {
 		t.Fatalf("mount was not requested: mount_working_dir=%v found=%v", mount, found)
 	}
+	// A bare prompt launches optimistically: no model preflight.
+	if verify, found := startVerify(t, envelopes); !found || verify {
+		t.Fatalf("bare prompt should launch with verify=false, got verify=%v found=%v", verify, found)
+	}
 	// setup.start leaves setup mode, so it must be the last command sent.
 	if start, instr := firstIndex(types, "setup.start"), lastIndex(types, "setup.set_instruction"); start < instr {
 		t.Fatalf("setup.start (%d) must come after setup.set_instruction (%d): %v", start, instr, types)
@@ -250,8 +273,9 @@ func TestSetupPromptWithTargetLaunches(t *testing.T) {
 			t.Fatalf("missing %s in %v", want, types)
 		}
 	}
-	if _, found := startPayloadFlag(t, envelopes, "mount_working_dir"); found {
-		t.Fatalf("a targeted prompt must not ask to mount the working directory: %v", types)
+	// A named target keeps the upfront model check.
+	if verify, found := startVerify(t, envelopes); !found || !verify {
+		t.Fatalf("targeted prompt should launch with verify=true, got verify=%v found=%v", verify, found)
 	}
 	// The target and instruction must reach the backend before setup.start
 	// closes the setup guard.
--- a/strix/interface/tui/runtime.py
+++ b/strix/interface/tui/runtime.py
@@ -63,14 +63,11 @@ class GoTuiRuntime:
        self.scan_error: BaseException | None = None
        self._last_sync_fingerprint = ""
        self._error_noted_agents: set[str] = set()
-        self.model_verified = False
-        self._setup_preflight: asyncio.Task[None] | None = None
        self.controller = TuiController(
            args,
            live_view=self.live_view,
            coordinator=self.coordinator,
            on_start=self.start_from_setup,
-            on_verify=self.ensure_model_verified,
            on_quit=self.quit,
        )
        self.server = TuiBackendServer(self.controller)
@@ -110,51 +107,7 @@ class GoTuiRuntime:
        )
        self.controller.notify_changed()

-    async def check_setup_model(self) -> None:
-        """Verify the model route as soon as the start screen is up.
-
-        The same round trip a direct launch makes in prepare_and_start, run in
-        the background so the screen paints first and the outcome lands in the
-        setup log before the user has finished typing.
-        """
-        if not (load_settings().llm.model or "").strip():
-            return
-        try:
-            await self._preflight_model()
-        except Exception as exc:
-            logger.exception("Go TUI setup model preflight failed")
-            self.controller.add_message(f"Model connection failed: {exc}", "error")
-            return
-        self.controller.add_message("Model connection verified")
-
-    async def ensure_model_verified(self) -> None:
-        """Hold a setup launch until the model has answered once."""
-        preflight = self._setup_preflight
-        if preflight is not None and not preflight.done():
-            await asyncio.shield(preflight)
-        if self.model_verified:
-            return
-        try:
-            await self._preflight_model()
-        except Exception as exc:
-            logger.exception("Go TUI setup model preflight failed")
-            raise RuntimeError(f"Model connection failed: {exc}") from exc
-
-    async def _preflight_model(self) -> None:
-        model = (load_settings().llm.model or "").strip()
-        self.controller.add_message("Verifying model connection...")
-        await preflight_model_connection(model)
-        self.model_verified = True
-
-    def _start_preparation(self) -> asyncio.Task[None]:
-        """Kick off the work that runs behind the freshly painted TUI."""
-        if self.controller.setup_mode:
-            self._setup_preflight = asyncio.create_task(self.check_setup_model())
-            return self._setup_preflight
-        self.controller.begin_preparation()
-        return asyncio.create_task(self.prepare_and_start())
-
-    async def start_from_setup(self) -> None:
+    async def start_from_setup(self, verify: bool = True) -> None:
        candidate = deepcopy(self.args)
        candidate.scan_mode = self.controller.scan_mode
        candidate.instruction = self.controller.instruction
@@ -171,7 +124,16 @@ class GoTuiRuntime:
            if isinstance(target, dict) and target.get("original")
        ]
        targets_changed = self.controller.targets != existing_targets
-        persist_current()
+        model = (load_settings().llm.model or "").strip()
+        # A bare prompt launches optimistically: it skips the network preflight
+        # and lets any model error surface once the agent starts, like a coding
+        # agent. A named target keeps the upfront check.
+        if verify:
+            try:
+                await preflight_model_connection(model)
+            except Exception as exc:
+                logger.exception("Go TUI setup model preflight failed")
+                raise RuntimeError(f"Model connection failed: {exc}") from exc
        # A confirmed target-less launch mounts the working directory for the
        # agent to work in, without making it a scan target.
        candidate.workspace_mount = self.controller.workspace_mount
@@ -414,7 +376,9 @@ class GoTuiRuntime:
                )
            process, backend_socket = await launch_tui_process(command, env, cwd)
            await self.server.start(backend_socket)
-            prepare_task = self._start_preparation()
+            if not self.controller.setup_mode:
+                self.controller.begin_preparation()
+                prepare_task = asyncio.create_task(self.prepare_and_start())
            sync_task = asyncio.create_task(self.sync_state())
            return_code = await wait_process(process)
            check_return_code(return_code)
--- a/strix/report/state.py
+++ b/strix/report/state.py
@@ -167,7 +167,7 @@ def get_global_report_state() -> Optional["ReportState"]:
    return _global_report_state


-def set_global_report_state(report_state: Optional["ReportState"]) -> None:
+def set_global_report_state(report_state: "ReportState") -> None:
    global _global_report_state  # noqa: PLW0603
    _global_report_state = report_state
    # New run: drop any streamed-cost entries a prior run left unconsumed.
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -24,30 +24,3 @@ def _isolate_mcp_config(
    monkeypatch.setenv("STRIX_MCP_CONFIG", str(missing))
    monkeypatch.delenv("STRIX_MCP_ONLY", raising=False)
    monkeypatch.delenv("STRIX_MCP_EXCLUDE", raising=False)
-
-
-@pytest.fixture(autouse=True)
-def _plain_terminal(monkeypatch: pytest.MonkeyPatch) -> None:
-    """Make Rich output identical on every developer's machine.
-
-    Many CLI tests force ``isatty()`` to ``True`` to exercise the human-readable
-    code path and then assert on the plain text. Rich picks its color system
-    from ``TERM``, ``COLORTERM``, and ``FORCE_COLOR``, so on a real terminal
-    those assertions would meet ANSI escape codes instead of the words they
-    look for. A dumb terminal renders the same text without any styling.
-    """
-    monkeypatch.setenv("TERM", "dumb")
-    for name in ("COLORTERM", "FORCE_COLOR", "NO_COLOR", "TTY_COMPATIBLE"):
-        monkeypatch.delenv(name, raising=False)
-
-
-@pytest.fixture(autouse=True)
-def _isolate_wallet_config(monkeypatch: pytest.MonkeyPatch) -> None:
-    """Keep a developer's real mppx wallet out of the top-up tests.
-
-    ``strix cloud billing topup`` chooses the Stripe Link flow or the
-    preconfigured mppx wallet from these variables, so leaving them set would
-    silently switch which branch a test runs.
-    """
-    for name in ("MPPX_ACCOUNT", "MPPX_STRIPE_SECRET_KEY", "MPPX_STRIPE_PAYMENT_METHOD"):
-        monkeypatch.delenv(name, raising=False)
--- a/tests/test_cloud_cli.py
+++ b/tests/test_cloud_cli.py
@@ -6,7 +6,6 @@ import io
 import json
 import shutil
 import subprocess
-import sys
 import urllib.request
 import webbrowser
 from pathlib import Path
@@ -17,7 +16,7 @@ import requests
 from rich.console import Console

 from strix.interface import cloud, platform_cli
-from strix.interface.cloud import http, render, runner, workspaces
+from strix.interface.cloud import billing, http, payment_proxy, render, runner, workspaces
 from strix.interface.cloud.spec import GROUP_HELP, SPEC


@@ -148,7 +147,7 @@ def test_read_groups_have_safe_defaults(group: str, verb: str) -> None:
    resolved = runner.resolve(group, [])
    assert resolved is not None
    command, remaining = resolved
-    assert command is SPEC[group][verb]
+    assert command is runner.SPEC[group][verb]
    assert remaining == []


@@ -562,7 +561,7 @@ def test_stored_token_is_never_sent_to_a_different_platform_origin(
        lambda: {"api_token": "stored-secret", "app_url": "https://app.strix.ai"},
    )
    monkeypatch.setattr(
-        requests,
+        http.requests,
        "request",
        lambda *_args, **_kwargs: pytest.fail("a mismatched origin must not receive the token"),
    )
@@ -577,7 +576,7 @@ def test_stored_token_requires_an_issuer_binding(monkeypatch: pytest.MonkeyPatch
    monkeypatch.setattr(http, "_app_url_override", "https://app.strix.ai")
    monkeypatch.setattr(http, "read_record", lambda: {"api_token": "legacy-secret"})
    monkeypatch.setattr(
-        requests,
+        http.requests,
        "request",
        lambda *_args, **_kwargs: pytest.fail("an unbound token must not be sent"),
    )
@@ -603,7 +602,7 @@ def test_stored_token_is_sent_only_to_its_bound_platform(
        seen.update(url=url, headers=kwargs["headers"])
        return FakeResponse(payload={"balance": 1})

-    monkeypatch.setattr(requests, "request", request)
+    monkeypatch.setattr(http.requests, "request", request)
    response = http.request("GET", "/billing/credits")

    assert response.status_code == 200
@@ -627,7 +626,7 @@ def test_explicit_token_can_target_an_explicit_platform(
        seen.update(url=url, headers=kwargs["headers"])
        return FakeResponse(payload={"balance": 1})

-    monkeypatch.setattr(requests, "request", request)
+    monkeypatch.setattr(http.requests, "request", request)
    override_value = "explicit-preview-" + str(1)
    response = http.request("GET", "/billing/credits", token=override_value)

@@ -707,9 +706,9 @@ def test_topup_noninteractive_requires_explicit_payment_approval(
    monkeypatch.setattr(
        http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload=challenge)
    )
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: False)
+    monkeypatch.setattr(runner.sys.stdin, "isatty", lambda: False)
    monkeypatch.setattr(
-        subprocess,
+        billing.subprocess,
        "run",
        lambda *_a, **_k: pytest.fail("wallet must not run without --yes"),
    )
@@ -733,10 +732,10 @@ def test_topup_machine_output_never_prompts_even_with_terminal_stdin(
    monkeypatch.setattr(
        http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload=challenge)
    )
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: True)
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: stdout_tty)
+    monkeypatch.setattr(runner.sys.stdin, "isatty", lambda: True)
+    monkeypatch.setattr(runner.sys.stdout, "isatty", lambda: stdout_tty)
    monkeypatch.setattr(
-        Console,
+        runner.Console,
        "input",
        lambda *_a, **_k: pytest.fail("machine-readable top-up must not prompt"),
    )
@@ -840,7 +839,7 @@ def test_topup_keeps_token_out_of_wallet_process_and_forwards_payment(
        upstream.update(method=method, url=url, **kwargs)
        return FakeResponse(payload=receipt, content=json.dumps(receipt).encode())

-    monkeypatch.setattr(requests, "request", fake_upstream_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_upstream_request)

    def fake_run(command: list[str], **kwargs: Any) -> Any:
        commands.append(command)
@@ -906,7 +905,6 @@ def test_topup_wallet_failure_is_one_redacted_json_object(
        http, "request", lambda *_a, **_k: FakeResponse(status_code=402, payload=challenge)
    )
    monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
    monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
    monkeypatch.setattr(
        subprocess,
@@ -948,7 +946,6 @@ def test_topup_wallet_interruption_reports_unknown_payment_outcome(
        ),
    )
    monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
    monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
    monkeypatch.setattr(
        subprocess, "run", lambda *_a, **_k: (_ for _ in ()).throw(KeyboardInterrupt)
@@ -974,7 +971,6 @@ def test_topup_non_json_wallet_success_requires_balance_verification(
        ),
    )
    monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
    monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
    monkeypatch.setattr(
        subprocess,
@@ -1001,7 +997,6 @@ def test_topup_rejects_parseable_wallet_error_as_a_success(
        ),
    )
    monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
    monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
    monkeypatch.setattr(
        subprocess,
@@ -1041,7 +1036,6 @@ def test_topup_does_not_trust_an_unobserved_wallet_receipt(
        ),
    )
    monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
    monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
    monkeypatch.setattr(
        subprocess,
@@ -1062,7 +1056,7 @@ def test_topup_does_not_trust_an_unobserved_wallet_receipt(
 def test_topup_human_mode_requires_a_bridge_confirmed_receipt(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -1072,10 +1066,9 @@ def test_topup_human_mode_requires_a_bridge_confirmed_receipt(
        ),
    )
    monkeypatch.setattr(http, "api_token", lambda *_a, **_k: "tok")
-    monkeypatch.setenv("MPPX_ACCOUNT", "agent")
    monkeypatch.setattr(shutil, "which", lambda _name: "/usr/bin/npx")
    monkeypatch.setattr(
-        requests,
+        payment_proxy.requests,
        "request",
        lambda *_a, **_k: FakeResponse(status_code=200, content=b"<html>not a receipt</html>"),
    )
@@ -1604,7 +1597,7 @@ def test_handoff_links_reject_non_http_schemes(
    monkeypatch: pytest.MonkeyPatch,
    capsys: Any,
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(runner.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -1889,7 +1882,7 @@ def test_workspace_use_preserves_definitive_conflict(
 def test_group_help_lists_all_verbs_instead_of_default_verb_help(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    assert cloud.run_cloud(["workspaces", "-h"]) == 0
    output = capsys.readouterr().out
    assert "workspaces verbs" in output
@@ -1913,7 +1906,7 @@ def test_workspace_alias_routes_to_workspaces(monkeypatch: pytest.MonkeyPatch) -
 def test_workspace_human_list_is_numbered_and_hides_ids(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -1961,7 +1954,7 @@ def test_integrations_human_list_exposes_installation_id_and_json_stays_full(
        ],
        "bitbucket_oauth_enabled": True,
    }
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))

    assert cloud.run_cloud(["integrations", "list"]) == 0
@@ -1979,7 +1972,7 @@ def test_integrations_human_list_exposes_installation_id_and_json_stays_full(
 def test_pr_review_human_list_prioritizes_actionable_fields(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -2054,7 +2047,7 @@ def test_pr_review_human_list_shows_pull_request_state(
    capsys: Any,
    pr_state: str,
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -2117,7 +2110,7 @@ def test_scan_human_list_identifies_internal_and_uploaded_targets(
    record: dict[str, Any],
    expected_targets: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -2281,7 +2274,7 @@ def test_human_lists_prioritize_actionable_fields(
    visible: tuple[str, ...],
    hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))

    assert cloud.run_cloud(command) == 0
@@ -2295,7 +2288,7 @@ def test_human_lists_prioritize_actionable_fields(
 def test_token_human_list_shows_lifecycle_status(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -2652,7 +2645,7 @@ def test_nonstandard_human_list_envelopes_are_actionable(
    visible: tuple[str, ...],
    hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))

    assert cloud.run_cloud(command) == 0
@@ -2702,7 +2695,7 @@ def test_chat_credentials_human_view_separates_attached_and_available_sources(
            }
        ],
    }
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))

    command = ["chat", "credentials", "chat-id", "--scan-ids", "source-scan-id"]
@@ -2928,7 +2921,7 @@ def test_named_human_list_views_match_api_fields(
    visible: tuple[str, ...],
    hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))

    assert cloud.run_cloud(command) == 0
@@ -2942,7 +2935,7 @@ def test_named_human_list_views_match_api_fields(
 def test_supply_chain_org_summary_human_view_shows_totals_and_repository_risk(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -3103,7 +3096,7 @@ def test_wrapped_detail_human_views_are_unwrapped_and_actionable(
    visible: tuple[str, ...],
    hidden: tuple[str, ...],
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(http, "request", lambda *_a, **_k: FakeResponse(payload=payload))

    assert cloud.run_cloud(command) == 0
@@ -3117,7 +3110,7 @@ def test_wrapped_detail_human_views_are_unwrapped_and_actionable(
 def test_trace_human_view_summarizes_events_and_preserves_selector(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    seen_query: dict[str, Any] = {}

    def fake_trace_request(_method: str, _path: str, **kwargs: Any) -> FakeResponse:
@@ -3213,7 +3206,7 @@ def test_trace_human_view_summarizes_events_and_preserves_selector(
 def test_paginated_human_list_shows_total_and_continuation_command(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -3315,7 +3308,7 @@ def test_page_pagination_explains_an_out_of_range_page() -> None:
 def test_human_detail_preserves_long_prose_beyond_table_cell_limit(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    description = (
        " ".join(["authorization context"] * 12) + " final-description-marker\nsecond-line-marker"
    )
@@ -3393,7 +3386,7 @@ def test_large_vulnerability_detail_prioritizes_evidence_and_remediation() -> No
 def test_test_user_human_view_joins_latest_verification(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -3490,7 +3483,7 @@ def test_wide_knowledge_table_keeps_title_readable_with_long_identifiers() -> No
 def test_human_get_prioritizes_details_and_hides_internal_identity_fields(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
--- a/tests/test_cloud_cli_runtime.py
+++ b/tests/test_cloud_cli_runtime.py
@@ -6,16 +6,13 @@ import argparse
 import io
 import json
 import sys
-import time
 from typing import TYPE_CHECKING, Any

 import pytest
-import requests
 from rich.console import Console

 from strix.interface import cloud, platform_cli
 from strix.interface.cloud import http, render, runner, source_scan
-from strix.interface.cloud.source_upload import prepare_source
 from strix.interface.main import main as interface_main


@@ -172,7 +169,7 @@ def test_connector_enrollment_command_is_complete_multiline_and_terminal_safe(
        "  -e LABEL=before\x1b]52;c;copied\x07after \\\n"
        "  ghcr.io/usestrix/connector:latest"
    )
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -296,8 +293,8 @@ def test_source_prompt_shows_paths_and_literal_confirmation(
        return "n"

    monkeypatch.setattr(console, "input", answer)
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: True)
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdin, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdout, "isatty", lambda: True)
    args = argparse.Namespace(
        source=str(tmp_path),
        dry_run=False,
@@ -327,7 +324,7 @@ def test_source_prompt_interruption_removes_temporary_archive(
    (tmp_path / "app.py").write_text("print('ok')\n", encoding="utf-8")
    console = Console(file=io.StringIO(), width=100)
    archive_paths: list[Path] = []
-    original_prepare = prepare_source
+    original_prepare = source_scan.prepare_source

    def capture_bundle(*args: Any, **kwargs: Any) -> Any:
        bundle = original_prepare(*args, **kwargs)
@@ -339,8 +336,8 @@ def test_source_prompt_interruption_removes_temporary_archive(

    monkeypatch.setattr(source_scan, "prepare_source", capture_bundle)
    monkeypatch.setattr(console, "input", interrupt)
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: True)
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdin, "isatty", lambda: True)
+    monkeypatch.setattr(source_scan.sys.stdout, "isatty", lambda: True)
    args = argparse.Namespace(
        source=str(tmp_path),
        dry_run=False,
@@ -397,7 +394,7 @@ def test_device_login_rejects_non_http_verification_url(
    monkeypatch: pytest.MonkeyPatch,
 ) -> None:
    monkeypatch.setattr(
-        requests,
+        platform_cli.requests,
        "post",
        lambda *_a, **_k: FakeResponse(
            {
@@ -430,7 +427,7 @@ def test_boolean_query_values_are_lowercase_for_url_search_params(
        seen["params"] = kwargs.get("params")
        return FakeResponse({"items": []})

-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(http.requests, "request", fake_request)
    http.request("GET", "/test", query={"enabled": True, "disabled": False})
    assert seen["params"] == {"enabled": "true", "disabled": "false"}

@@ -484,7 +481,7 @@ def test_binary_response_refuses_to_write_to_a_terminal(
    monkeypatch: pytest.MonkeyPatch,
    capsys: Any,
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(runner.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
@@ -516,7 +513,7 @@ def test_binary_response_can_be_intentionally_redirected(
            return None

    redirected = RedirectedStdout()
-    monkeypatch.setattr(sys, "stdout", redirected)
+    monkeypatch.setattr(runner.sys, "stdout", redirected)
    monkeypatch.setattr(
        http,
        "request",
@@ -537,7 +534,7 @@ def test_redirected_binary_errors_never_append_diagnostics_to_stdout(
        def iter_content(self, *, chunk_size: int) -> Any:
            assert chunk_size == 1024 * 1024
            yield b"%PDF-partial"
-            raise requests.ConnectionError("connection lost")
+            raise http.requests.ConnectionError("connection lost")

    response = (
        FakeResponse({"detail": "report rejected"}, status_code=500)
@@ -648,7 +645,7 @@ def test_binary_download_streams_and_preserves_existing_file_on_failure(
        def iter_content(self, *, chunk_size: int) -> Any:
            assert chunk_size == 1024 * 1024
            yield b"partial"
-            raise requests.ConnectionError("connection lost")
+            raise http.requests.ConnectionError("connection lost")

        def close(self) -> None:
            self.closed = True
@@ -773,7 +770,7 @@ def test_session_help_is_specific_and_human_whoami_shows_scopes(
            "scopes": ["scans:read", "organizations:read"],
        }
    )
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(platform_cli.sys.stdout, "isatty", lambda: True)
    assert cloud.run_cloud(["whoami", "--help"]) == 0
    who_help = capsys.readouterr().out
    assert "strix cloud whoami" in who_help
@@ -787,7 +784,7 @@ def test_non_tty_whoami_and_logout_emit_json(
 ) -> None:
    monkeypatch.delenv("STRIX_API_TOKEN", raising=False)
    monkeypatch.setattr(platform_cli, "AUTH_PATH", tmp_path / "auth.json")
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: False)
+    monkeypatch.setattr(platform_cli.sys.stdout, "isatty", lambda: False)
    platform_cli.save_record(
        {
            "api_token": "secret",
@@ -802,7 +799,7 @@ def test_non_tty_whoami_and_logout_emit_json(
    assert json.loads(capsys.readouterr().out)["email"] == "agent@example.test"

    monkeypatch.setattr(
-        requests,
+        platform_cli.requests,
        "delete",
        lambda *_args, **_kwargs: type("Response", (), {"status_code": 200})(),
    )
@@ -834,7 +831,7 @@ def test_scope_picker_labels_match_the_server_presets() -> None:
 def test_noninteractive_login_never_prompts_for_workspace(
    monkeypatch: pytest.MonkeyPatch,
 ) -> None:
-    monkeypatch.setattr(sys.stdin, "isatty", lambda: False)
+    monkeypatch.setattr(platform_cli.sys.stdin, "isatty", lambda: False)
    console = Console(file=io.StringIO())
    console.input = lambda *_args, **_kwargs: pytest.fail("must not prompt")  # type: ignore[method-assign]

@@ -899,10 +896,10 @@ def test_device_flow_slow_down_never_exceeds_the_poll_interval_cap(
        sleeps.append(seconds)
        now += seconds

-    monkeypatch.setattr(requests, "post", post)
+    monkeypatch.setattr(platform_cli.requests, "post", post)
    monkeypatch.setattr(platform_cli, "_app_url", lambda: "https://example.test")
-    monkeypatch.setattr(time, "monotonic", monotonic)
-    monkeypatch.setattr(time, "sleep", sleep)
+    monkeypatch.setattr(platform_cli.time, "monotonic", monotonic)
+    monkeypatch.setattr(platform_cli.time, "sleep", sleep)

    with pytest.raises(platform_cli.PlatformAuthError, match="expired"):
        platform_cli._run_device_flow(
@@ -936,9 +933,9 @@ def test_device_flow_accepts_external_authkit_url_and_binds_token_origin(
            ),
        ]
    )
-    monkeypatch.setattr(requests, "post", lambda *_a, **_k: next(responses))
+    monkeypatch.setattr(platform_cli.requests, "post", lambda *_a, **_k: next(responses))
    monkeypatch.setattr(platform_cli, "_app_url", lambda: "https://preview.strix.ai")
-    monkeypatch.setattr(time, "sleep", lambda _seconds: None)
+    monkeypatch.setattr(platform_cli.time, "sleep", lambda _seconds: None)

    record = platform_cli._run_device_flow(
        Console(file=io.StringIO()),
@@ -987,7 +984,7 @@ def test_root_help_accepts_json_before_help_and_leaf_help_stays_specific(
 def test_non_tty_dispatcher_always_emits_structured_json(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: False)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: False)

    assert cloud.run_cloud([]) == 0
    assert json.loads(capsys.readouterr().out)["command"] == "strix cloud"
@@ -1023,7 +1020,7 @@ def test_source_upload_rejects_untrusted_destinations_before_reading_file(
    source.write_bytes(b"approved source")
    monkeypatch.setattr(http, "_app_url_override", "https://app.strix.ai")
    monkeypatch.setattr(
-        requests,
+        http.requests,
        "put",
        lambda *_args, **_kwargs: pytest.fail("an untrusted URL must not receive source bytes"),
    )
@@ -1062,7 +1059,7 @@ def test_source_upload_allows_only_managed_or_same_origin_storage(
        return response

    monkeypatch.setattr(http, "_app_url_override", app_url)
-    monkeypatch.setattr(requests, "put", put)
+    monkeypatch.setattr(http.requests, "put", put)
    http.upload_file(signed_url, "upload-token", source)

    assert request_options["allow_redirects"] is False
@@ -1083,7 +1080,7 @@ def test_source_upload_refuses_redirects_without_following_them(
        return response

    monkeypatch.setattr(http, "_app_url_override", "https://app.strix.ai")
-    monkeypatch.setattr(requests, "put", put)
+    monkeypatch.setattr(http.requests, "put", put)

    with pytest.raises(http.CloudError, match="unexpected redirect"):
        http.upload_file(
@@ -1098,7 +1095,7 @@ def test_source_upload_refuses_redirects_without_following_them(
 def test_one_time_api_token_has_save_now_warning(
    monkeypatch: pytest.MonkeyPatch, capsys: Any
 ) -> None:
-    monkeypatch.setattr(sys.stdout, "isatty", lambda: True)
+    monkeypatch.setattr(render.sys.stdout, "isatty", lambda: True)
    monkeypatch.setattr(
        http,
        "request",
--- a/tests/test_cloud_idempotency.py
+++ b/tests/test_cloud_idempotency.py
@@ -3,11 +3,9 @@
 from __future__ import annotations

 import json
-import time
 from typing import Any

 import pytest
-import requests

 from strix.interface import cloud
 from strix.interface.cloud import http, runner
@@ -32,7 +30,7 @@ class FakeResponse:
@pytest.fixture(autouse=True)
 def _token(monkeypatch: pytest.MonkeyPatch) -> None:
    monkeypatch.setenv("STRIX_API_TOKEN", "idempotency-test-token")
-    monkeypatch.setattr(time, "sleep", lambda _seconds: None)
+    monkeypatch.setattr(runner.time, "sleep", lambda _seconds: None)


 def test_scan_start_generates_and_sends_one_stable_key(
@@ -199,7 +197,7 @@ def test_http_client_places_key_in_the_header(monkeypatch: pytest.MonkeyPatch) -
        seen.update(kwargs)
        return FakeResponse({"ok": True})

-    monkeypatch.setattr(requests, "request", request)
+    monkeypatch.setattr(http.requests, "request", request)
    http.request("POST", "/scans", body={}, idempotency_key="header-key")
    assert seen["headers"]["Idempotency-Key"] == "header-key"
    assert seen["headers"]["Authorization"] == "Bearer idempotency-test-token"
--- a/tests/test_cloud_payment_proxy.py
+++ b/tests/test_cloud_payment_proxy.py
@@ -7,7 +7,6 @@ import urllib.request
 from typing import TYPE_CHECKING, Any

 import pytest
-import requests

 from strix.interface.cloud import payment_proxy

@@ -40,8 +39,7 @@ def _post(url: str, body: bytes, headers: dict[str, str] | None = None) -> bytes
        method="POST",
    )
    with urllib.request.urlopen(request, timeout=2) as response:  # noqa: S310
-        body_bytes: bytes = response.read()
-    return body_bytes
+        return response.read()


 def test_bridge_bounds_decompressed_upstream_response(monkeypatch: pytest.MonkeyPatch) -> None:
@@ -52,7 +50,7 @@ def test_bridge_bounds_decompressed_upstream_response(monkeypatch: pytest.Monkey
        return response

    monkeypatch.setattr(payment_proxy, "_MAX_UPSTREAM_RESPONSE_BYTES", 4)
-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_request)

    with payment_proxy.wallet_payment_bridge(
        upstream_url="https://app.example.test/api/v1/billing/topup",
@@ -82,7 +80,7 @@ def test_bridge_forwards_only_the_approved_request_and_protected_headers(
        captured.append(kwargs)
        return _StreamingResponse([b'{"ok":true}'])

-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_request)
    with payment_proxy.wallet_payment_bridge(
        upstream_url="https://app.example.test/api/v1/billing/topup",
        api_token="strix-secret",  # noqa: S106
@@ -126,7 +124,7 @@ def test_bridge_limits_valid_wallet_attempts(monkeypatch: pytest.MonkeyPatch) ->
        calls += 1
        return _StreamingResponse([b"{}"])

-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(payment_proxy.requests, "request", fake_request)
    with payment_proxy.wallet_payment_bridge(
        upstream_url="https://app.example.test/api/v1/billing/topup",
        api_token="strix-secret",  # noqa: S106
--- a/tests/test_cloud_session.py
+++ b/tests/test_cloud_session.py
@@ -6,7 +6,6 @@ import json
 from typing import TYPE_CHECKING, Any

 import pytest
-import requests
 from rich.console import Console

 from strix.interface import cloud, platform_cli, platform_identity
@@ -56,7 +55,7 @@ def test_http_workspace_pin_is_captured_once(
        sent.append(dict(kwargs["headers"]))
        return Response({})

-    monkeypatch.setattr(requests, "request", fake_request)
+    monkeypatch.setattr(http.requests, "request", fake_request)
    http.configure()
    platform_cli.save_record(
        {
@@ -117,7 +116,7 @@ def test_logout_keeps_local_token_when_remote_outcome_is_not_definitive(
        }
    )
    monkeypatch.setattr(
-        requests,
+        platform_cli.requests,
        "delete",
        lambda *_args, **_kwargs: Response({"detail": "unavailable"}, 503),
    )
--- a/tests/test_docker_client_delete.py
+++ b/tests/test_docker_client_delete.py
@@ -12,7 +12,6 @@ would let it escape and surface a traceback on every teardown.
 from __future__ import annotations

 from types import SimpleNamespace
-from typing import TYPE_CHECKING, cast
 from unittest.mock import AsyncMock, MagicMock, patch

 import pytest
@@ -23,10 +22,6 @@ from requests.exceptions import ConnectionError as RequestsConnectionError
 from strix.runtime.docker_client import StrixDockerSandboxClient


-if TYPE_CHECKING:
-    from agents.sandbox.session.sandbox_session import SandboxSession
-
-
 def _client_with_kill_error(exc: Exception) -> StrixDockerSandboxClient:
    """A StrixDockerSandboxClient whose containers.get(...).kill() raises ``exc``."""
    client = StrixDockerSandboxClient.__new__(StrixDockerSandboxClient)
@@ -36,10 +31,9 @@ def _client_with_kill_error(exc: Exception) -> StrixDockerSandboxClient:
    return client


-def _session(container_id: str | None = "abc123") -> SandboxSession:
+def _session() -> object:
    # delete() reads session._inner.state.container_id
-    fake = SimpleNamespace(_inner=SimpleNamespace(state=SimpleNamespace(container_id=container_id)))
-    return cast("SandboxSession", fake)
+    return SimpleNamespace(_inner=SimpleNamespace(state=SimpleNamespace(container_id="abc123")))


@pytest.mark.parametrize(
@@ -51,7 +45,7 @@ def _session(container_id: str | None = "abc123") -> SandboxSession:
    ],
 )
@pytest.mark.asyncio
-async def test_delete_swallows_best_effort_kill_errors(exc: Exception) -> None:
+async def test_delete_swallows_best_effort_kill_errors(exc):
    """A torn-down socket (ConnectionError) or a gone/unhappy container
    (NotFound/APIError) during the kill must not propagate; delete() still
    delegates to the SDK's delete()."""
@@ -68,7 +62,7 @@ async def test_delete_swallows_best_effort_kill_errors(exc: Exception) -> None:


@pytest.mark.asyncio
-async def test_delete_does_not_swallow_unrelated_errors() -> None:
+async def test_delete_does_not_swallow_unrelated_errors():
    """A programming error (e.g. ValueError) is not part of best-effort kill and
    must still propagate."""
    client = _client_with_kill_error(ValueError("boom"))
@@ -77,11 +71,11 @@ async def test_delete_does_not_swallow_unrelated_errors() -> None:


@pytest.mark.asyncio
-async def test_delete_noop_without_container_id() -> None:
+async def test_delete_noop_without_container_id():
    """No container_id -> no kill attempt, just delegate."""
    client = StrixDockerSandboxClient.__new__(StrixDockerSandboxClient)
    client.docker_client = MagicMock()
-    session = _session(container_id=None)
+    session = SimpleNamespace(_inner=SimpleNamespace(state=SimpleNamespace(container_id=None)))

    with patch.object(
        DockerSandboxClient, "delete", new=AsyncMock(return_value=session)
--- a/tests/test_go_tui_runtime.py
+++ b/tests/test_go_tui_runtime.py
@@ -343,19 +343,15 @@ async def test_setup_preflights_model_before_starting(
        assert candidate.scope_mode == "diff"
        assert candidate.diff_base == "origin/main"

-    monkeypatch.setattr(go_tui, "persist_current", lambda: calls.append("persist"))
    monkeypatch.setattr(go_tui, "build_targets_info", build)
    monkeypatch.setattr(go_tui, "prepare_run", prepare)
    monkeypatch.setattr(go_tui, "telemetry_start", lambda _args: calls.append("telemetry"))
    monkeypatch.setattr(runtime, "init_run_state", lambda: calls.append("state"))
    monkeypatch.setattr(runtime, "start_scan", lambda: calls.append("scan"))

-    # The controller runs these two in turn for every setup launch.
-    await runtime.ensure_model_verified()
    await runtime.start_from_setup()

-    # The same steps, in the same order, as a direct launch's prepare_and_start.
-    assert calls == ["preflight", "persist", "targets", "prepare", "telemetry", "state", "scan"]
+    assert calls == ["preflight", "targets", "prepare", "telemetry", "state", "scan"]
    assert runtime.args.scan_mode == "quick"
    assert runtime.args.instruction == ""
    assert runtime.args.max_budget_usd == 8.5
@@ -364,138 +360,35 @@ async def test_setup_preflights_model_before_starting(
    assert runtime.args.diff_base == "origin/main"


-def _setup_model(
-    monkeypatch: pytest.MonkeyPatch, model: str | None = "openrouter/test-model"
+@pytest.mark.asyncio
+async def test_optimistic_setup_skips_model_preflight(
+    monkeypatch: pytest.MonkeyPatch,
 ) -> None:
+    runtime = GoTuiRuntime(args())
+    runtime.controller.targets = [str(Path.cwd())]
+    calls: list[str] = []
+
+    async def preflight(_model: str) -> None:
+        calls.append("preflight")
+
    monkeypatch.setattr(
        go_tui,
        "load_settings",
-        lambda: SimpleNamespace(llm=SimpleNamespace(model=model)),
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
    )
-
-
-def _setup_messages(runtime: GoTuiRuntime) -> list[tuple[str, str]]:
-    return [(message["level"], message["text"]) for message in runtime.controller.messages]
-
-
-@pytest.mark.asyncio
-async def test_setup_model_check_reports_success_in_the_setup_log(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-    calls: list[str] = []
-
-    async def preflight(model: str) -> None:
-        calls.append(model)
-
-    _setup_model(monkeypatch)
    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
+    monkeypatch.setattr(go_tui, "build_targets_info", lambda _args, **_kw: calls.append("targets"))
+    monkeypatch.setattr(go_tui, "prepare_run", lambda _args: calls.append("prepare"))
+    monkeypatch.setattr(go_tui, "telemetry_start", lambda _args: calls.append("telemetry"))
+    monkeypatch.setattr(runtime, "init_run_state", lambda: calls.append("state"))
+    monkeypatch.setattr(runtime, "start_scan", lambda: calls.append("scan"))

-    await runtime.check_setup_model()
+    await runtime.start_from_setup(verify=False)

-    assert calls == ["openrouter/test-model"]
-    assert runtime.model_verified is True
-    assert _setup_messages(runtime) == [
-        ("info", "Verifying model connection..."),
-        ("info", "Model connection verified"),
-    ]
-
-
-@pytest.mark.asyncio
-async def test_setup_model_check_reports_failure_without_leaving_setup(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-
-    async def preflight(_model: str) -> None:
-        raise TimeoutError("connection timed out")
-
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-
-    await runtime.check_setup_model()
-
-    assert runtime.model_verified is False
-    assert runtime.controller.setup_mode is True
-    assert runtime.controller.scan_state == "setup"
-    assert _setup_messages(runtime)[-1] == (
-        "error",
-        "Model connection failed: connection timed out",
-    )
-
-
-@pytest.mark.asyncio
-async def test_setup_model_check_waits_for_a_configured_model(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-
-    _setup_model(monkeypatch, model=None)
-    monkeypatch.setattr(
-        go_tui,
-        "preflight_model_connection",
-        lambda _model: pytest.fail("nothing to check without a model"),
-    )
-
-    await runtime.check_setup_model()
-
-    assert runtime.model_verified is False
-    assert runtime.controller.messages == []
-
-
-@pytest.mark.asyncio
-async def test_ensure_model_verified_reuses_the_startup_check(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-    release = asyncio.Event()
-    calls: list[str] = []
-
-    async def preflight(_model: str) -> None:
-        calls.append("preflight")
-        await release.wait()
-
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-    runtime._setup_preflight = asyncio.create_task(runtime.check_setup_model())
-    await asyncio.sleep(0)
-
-    # A launch that arrives mid-check waits for it rather than racing a second
-    # round trip.
-    ensure = asyncio.create_task(runtime.ensure_model_verified())
-    await asyncio.sleep(0)
-    assert not ensure.done()
-    release.set()
-    await ensure
-
-    assert calls == ["preflight"]
-    assert runtime.model_verified is True
-
-
-@pytest.mark.asyncio
-async def test_ensure_model_verified_retries_after_a_failed_startup_check(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    runtime = GoTuiRuntime(args())
-    outcomes = iter([TimeoutError("connection timed out"), None])
-    calls: list[str] = []
-
-    async def preflight(_model: str) -> None:
-        calls.append("preflight")
-        outcome = next(outcomes)
-        if outcome is not None:
-            raise outcome
-
-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-
-    await runtime.check_setup_model()
-    assert runtime.model_verified is False
-
-    await runtime.ensure_model_verified()
-
-    assert calls == ["preflight", "preflight"]
-    assert runtime.model_verified is True
+    # No preflight: the scan launches straight through and any model error
+    # surfaces once the agent runs.
+    assert "preflight" not in calls
+    assert calls == ["targets", "prepare", "telemetry", "state", "scan"]


@pytest.mark.asyncio
@@ -507,8 +400,15 @@ async def test_confirmed_target_less_launch_mounts_workspace_without_targets(
    runtime.controller.workspace_mount = str(Path.home())
    prepared: list[argparse.Namespace] = []

-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "persist_current", lambda: None)
+    async def preflight(_model: str) -> None:
+        return None
+
+    monkeypatch.setattr(
+        go_tui,
+        "load_settings",
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
+    )
+    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
    monkeypatch.setattr(
        go_tui,
        "build_targets_info",
@@ -519,7 +419,7 @@ async def test_confirmed_target_less_launch_mounts_workspace_without_targets(
    monkeypatch.setattr(runtime, "init_run_state", lambda: None)
    monkeypatch.setattr(runtime, "start_scan", lambda: None)

-    await runtime.start_from_setup()
+    await runtime.start_from_setup(verify=False)

    assert prepared[0].workspace_mount == str(Path.home())
    assert prepared[0].targets_info == []
@@ -542,8 +442,15 @@ async def test_setup_preserves_prepared_cli_targets(
    runtime = GoTuiRuntime(runtime_args)
    calls: list[str] = []

-    _setup_model(monkeypatch)
-    monkeypatch.setattr(go_tui, "persist_current", lambda: calls.append("persist"))
+    async def preflight(_model: str) -> None:
+        calls.append("preflight")
+
+    monkeypatch.setattr(
+        go_tui,
+        "load_settings",
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
+    )
+    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
    monkeypatch.setattr(
        go_tui,
        "build_targets_info",
@@ -558,7 +465,7 @@ async def test_setup_preserves_prepared_cli_targets(

    assert runtime.controller.targets == ["https://example.com"]
    assert runtime.args.targets_info[0]["type"] == "web"
-    assert calls == ["persist", "prepare", "telemetry", "state", "scan"]
+    assert calls == ["preflight", "prepare", "telemetry", "state", "scan"]


@pytest.mark.asyncio
@@ -891,17 +798,19 @@ async def test_setup_preflight_failure_does_not_start_scan(
        nonlocal started
        started = True

-    _setup_model(monkeypatch)
+    monkeypatch.setattr(
+        go_tui,
+        "load_settings",
+        lambda: SimpleNamespace(llm=SimpleNamespace(model="openrouter/test-model")),
+    )
    monkeypatch.setattr(go_tui, "preflight_model_connection", preflight)
-    monkeypatch.setattr(go_tui, "persist_current", mark_started)
    monkeypatch.setattr(go_tui, "build_targets_info", mark_started)
    monkeypatch.setattr(runtime, "init_run_state", mark_started)
    monkeypatch.setattr(runtime, "start_scan", mark_started)

    with pytest.raises(RuntimeError, match="Model connection failed: 401 Unauthorized"):
-        await runtime.ensure_model_verified()
+        await runtime.start_from_setup()

-    assert runtime.model_verified is False
    assert started is False
    assert runtime.scan_task is None

--- a/tests/test_models.py
+++ b/tests/test_models.py
@@ -72,13 +72,6 @@ def test_recommended_models_are_matched_case_insensitively() -> None:
        "moonshot/kimi-k2.6",
        "kimi-k2.7-code",
        "moonshot/kimi-k3",
-        "anthropic/claude-fable-5-1",
-        "vertex_ai/claude-fable-5-1@default",
-        "gemini/gemini-3.7-flash",
-        "glm-5.3",
-        "zai/glm-5.3-flash",
-        "openrouter/z-ai/glm-5.3",
-        "novita/zai-org/glm-5.2",
    ],
 )
 def test_frontier_model_families_are_accepted(model_name: str) -> None:
@@ -99,9 +92,6 @@ def test_frontier_model_families_are_accepted(model_name: str) -> None:
        "openrouter/x-ai/grok-4",
        "mistral/mistral-medium-3-5",
        "mistral/magistral-medium-latest",
-        "zai/glm-4.7",
-        "openrouter/z-ai/glm-5",
-        "custom-provider/glm-5.3-local",
    ],
 )
 def test_non_frontier_models_are_rejected(model_name: str) -> None:
--- a/tests/test_optional_deps.py
+++ b/tests/test_optional_deps.py
@@ -11,8 +11,7 @@ PYPROJECT = Path(__file__).resolve().parent.parent / "pyproject.toml"

 def _optional_dependencies() -> dict[str, list[str]]:
    data = tomllib.loads(PYPROJECT.read_text(encoding="utf-8"))
-    extras: dict[str, list[str]] = data["project"]["optional-dependencies"]
-    return extras
+    return data["project"]["optional-dependencies"]


 def test_vertex_extra_pins_google_auth() -> None:
--- a/tests/test_runner_mcp.py
+++ b/tests/test_runner_mcp.py
@@ -185,4 +185,6 @@ async def test_roster_is_persisted_even_without_a_status_sink(
    )

    assert persisted, "roster must persist even when no status sink is attached"
-    assert persisted[-1] == [{"name": "local_fs", "provider": None, "tool_count": 3, "dead": False}]
+    assert persisted[-1] == [
+        {"name": "local_fs", "provider": None, "tool_count": 3, "dead": False}
+    ]
--- a/tests/test_sarif_stride.py
+++ b/tests/test_sarif_stride.py
@@ -34,8 +34,7 @@ def _finding(**overrides: Any) -> dict[str, Any]:


 def _rule_tags(doc: dict[str, Any]) -> list[str]:
-    tags: list[str] = doc["runs"][0]["tool"]["driver"]["rules"][0]["properties"]["tags"]
-    return tags
+    return doc["runs"][0]["tool"]["driver"]["rules"][0]["properties"]["tags"]


 def test_stride_tags_on_rule_for_known_cwe() -> None:
--- a/tests/test_session_fd.py
+++ b/tests/test_session_fd.py
@@ -1,7 +1,6 @@
 from __future__ import annotations

 import asyncio
-import os
 from pathlib import Path
 from typing import Any, cast

@@ -10,40 +9,13 @@ import pytest
 from strix.core.sessions import open_agent_session


-def _fd_dir() -> Path | None:
+def _count_open_fds() -> int | None:
    for path in (Path("/proc/self/fd"), Path("/dev/fd")):
        if path.is_dir():
-            return path
+            return len(list(path.iterdir()))
    return None


-def _count_open_fds() -> int | None:
-    fd_dir = _fd_dir()
-    return None if fd_dir is None else len(list(fd_dir.iterdir()))
-
-
-def _count_open_fds_to(files: list[Path]) -> int | None:
-    """Count the descriptors this process holds on exactly ``files``.
-
-    Matching on inode rather than on the process-wide total keeps the check
-    immune to sockets and pipes that unrelated background threads open while
-    the test runs.
-    """
-    fd_dir = _fd_dir()
-    if fd_dir is None:
-        return None
-    wanted = {(stat.st_dev, stat.st_ino) for stat in (path.stat() for path in files)}
-    held = 0
-    for entry in fd_dir.iterdir():
-        try:
-            stat = os.fstat(int(entry.name))
-        except (OSError, ValueError):
-            continue
-        if (stat.st_dev, stat.st_ino) in wanted:
-            held += 1
-    return held
-
-
@pytest.mark.asyncio
 async def test_sessions_hold_no_descriptors_while_parked(tmp_path: Path) -> None:
    """Descriptor use must track live operations, not the number of sessions.
@@ -53,20 +25,21 @@ async def test_sessions_hold_no_descriptors_while_parked(tmp_path: Path) -> None
    scan, and fan-out multiplies those handles until the process runs out of file
    descriptors (#1018). A session that is not mid-operation should hold none.
    """
-    if _fd_dir() is None:
+    baseline = _count_open_fds()
+    if baseline is None:
        pytest.skip("no /proc/self/fd or /dev/fd on this platform")

-    db_paths = [tmp_path / f"s{i}.db" for i in range(60)]
-    sessions = [open_agent_session(f"a{i}", path) for i, path in enumerate(db_paths)]
+    sessions = [open_agent_session(f"a{i}", tmp_path / f"s{i}.db") for i in range(60)]
    try:
        for _ in range(4):
            await asyncio.gather(
                *(s.add_items([{"role": "user", "content": "x"}]) for s in sessions)
            )
            await asyncio.gather(*(s.get_items() for s in sessions))
-        parked = _count_open_fds_to(db_paths)
-        # 60 parked sessions, yet none of them holds its database open.
-        assert parked == 0, f"parked sessions hold {parked} database descriptors"
+        parked = _count_open_fds()
+        assert parked is not None
+        # 60 parked sessions, yet descriptors are back at the baseline.
+        assert parked - baseline <= 5, f"parked fds grew by {parked - baseline}"
    finally:
        for s in sessions:
            s.close()
--- a/tests/test_tui_backend_controller.py
+++ b/tests/test_tui_backend_controller.py
@@ -155,7 +155,7 @@ def test_setup_restores_prepared_cli_targets() -> None:
 async def test_start_validates_model_before_callback() -> None:
    started = False

-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
        nonlocal started
        started = True

@@ -170,7 +170,7 @@ async def test_start_validates_model_before_callback() -> None:
 async def test_start_launches_with_a_configured_model() -> None:
    started = False

-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
        nonlocal started
        started = True

@@ -189,7 +189,7 @@ async def test_start_launches_with_a_configured_model() -> None:
 async def test_start_without_target_requires_mount_consent() -> None:
    started = False

-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
        nonlocal started
        started = True

@@ -200,7 +200,7 @@ async def test_start_without_target_requires_mount_consent() -> None:

    # Mounting the working directory is never silent.
    with pytest.raises(ValueError, match="No target set"):
-        await controller.handle("setup.start", {})
+        await controller.handle("setup.start", {"verify": False})
    assert started is False
    assert controller.targets == []
    assert controller.workspace_mount is None
@@ -211,7 +211,7 @@ async def test_target_less_start_enters_live_view_and_waits_for_the_mount() -> N
    """Nothing is prepared until the live-view confirmation is answered."""
    started = False

-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
        nonlocal started
        started = True

@@ -220,7 +220,7 @@ async def test_target_less_start_enters_live_view_and_waits_for_the_mount() -> N
    loader._cached = None
    controller = TuiController(args(), on_start=start)

-    result = await controller.handle("setup.start", {"mount_working_dir": True})
+    result = await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})

    assert result == {"started": True}
    # The live view is up so the prompt can be shown there, but the scan has not
@@ -236,23 +236,26 @@ async def test_target_less_start_enters_live_view_and_waits_for_the_mount() -> N
@pytest.mark.asyncio
 async def test_confirming_the_mount_starts_the_scan_without_a_target() -> None:
    started = False
+    seen_verify: bool | None = None

-    async def start() -> None:
-        nonlocal started
+    async def start(verify: bool = True) -> None:
+        nonlocal started, seen_verify
        started = True
+        seen_verify = verify

    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
    os.environ["ANTHROPIC_API_KEY"] = "test-key"
    loader._cached = None
    controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})

    result = await controller.handle("setup.confirm_mount", {"approved": True})

    assert result == {"approved": True}
    assert started is True
-    # Mounted as a workspace: the scan genuinely has no target, so the
-    # instruction is the only source of truth.
+    # Launched optimistically, and mounted as a workspace: the scan genuinely
+    # has no target, so the instruction is the only source of truth.
+    assert seen_verify is False
    assert controller.workspace_mount == str(Path.cwd())
    assert controller.targets == []
    assert controller.scan_state == "running"
@@ -261,23 +264,22 @@ async def test_confirming_the_mount_starts_the_scan_without_a_target() -> None:

@pytest.mark.asyncio
 async def test_declining_the_mount_runs_without_one() -> None:
-    started = 0
+    started: list[bool] = []

-    async def start() -> None:
-        nonlocal started
-        started += 1
+    async def start(verify: bool = True) -> None:
+        started.append(verify)

    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
    os.environ["ANTHROPIC_API_KEY"] = "test-key"
    loader._cached = None
    controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})

    result = await controller.handle("setup.confirm_mount", {"approved": False})

    assert result == {"approved": False}
    # Declining skips the directory; it does not abandon the scan.
-    assert started == 1
+    assert started == [False]
    assert controller.workspace_mount is None
    assert controller.pending_workspace_mount is None
    assert controller.setup_mode is False
@@ -287,22 +289,21 @@ async def test_declining_the_mount_runs_without_one() -> None:

@pytest.mark.asyncio
 async def test_approving_the_mount_runs_with_it() -> None:
-    started = 0
+    started: list[bool] = []

-    async def start() -> None:
-        nonlocal started
-        started += 1
+    async def start(verify: bool = True) -> None:
+        started.append(verify)

    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
    os.environ["ANTHROPIC_API_KEY"] = "test-key"
    loader._cached = None
    controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})

    result = await controller.handle("setup.confirm_mount", {"approved": True})

    assert result == {"approved": True}
-    assert started == 1
+    assert started == [False]
    assert controller.workspace_mount == str(Path.cwd())
    assert controller.scan_state == "running"

@@ -351,91 +352,23 @@ async def test_user_message_updates_live_agent_projection_immediately() -> None:


@pytest.mark.asyncio
-async def test_start_verifies_the_model_before_a_targeted_launch() -> None:
-    order: list[str] = []
+async def test_start_forwards_verify_flag_by_default() -> None:
+    seen_verify: bool | None = None

-    async def verify() -> None:
-        order.append("verify")
-
-    async def start() -> None:
-        order.append("start")
-
-    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
-    os.environ["ANTHROPIC_API_KEY"] = "test-key"
-    loader._cached = None
-    controller = TuiController(args(), on_start=start, on_verify=verify)
-    await controller.handle("setup.add_target", {"target": "https://example.com"})
-
-    await controller.handle("setup.start", {})
-
-    assert order == ["verify", "start"]
-
-
-@pytest.mark.asyncio
-async def test_start_verifies_the_model_before_a_bare_prompt_leaves_setup() -> None:
-    """A bare prompt gets the same model check as a named target, while the
-    setup log is still on screen to show the outcome."""
-    verified = 0
-
-    async def verify() -> None:
-        nonlocal verified
-        verified += 1
-
-    async def start() -> None:
-        return None
-
-    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
-    os.environ["ANTHROPIC_API_KEY"] = "test-key"
-    loader._cached = None
-    controller = TuiController(args(), on_start=start, on_verify=verify)
-
-    await controller.handle("setup.start", {"mount_working_dir": True})
-
-    assert verified == 1
-    assert controller.setup_mode is False
-    assert controller.pending_workspace_mount == str(Path.cwd())
-
-
-@pytest.mark.asyncio
-async def test_failed_model_check_keeps_the_start_screen() -> None:
-    async def verify() -> None:
-        raise RuntimeError("Model connection failed: timed out")
-
-    async def start() -> None:
-        pytest.fail("the scan must not start when the model check fails")
-
-    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
-    os.environ["ANTHROPIC_API_KEY"] = "test-key"
-    loader._cached = None
-    controller = TuiController(args(), on_start=start, on_verify=verify)
-
-    with pytest.raises(RuntimeError, match="Model connection failed"):
-        await controller.handle("setup.start", {"mount_working_dir": True})
-
-    # Still on the start screen, so the error lands in the setup log and the
-    # user can retry; no run was prepared behind a stuck live view.
-    assert controller.setup_mode is True
-    assert controller.scan_started is False
-    assert controller.scan_state == "setup"
-    assert controller.pending_workspace_mount is None
-
-
-@pytest.mark.asyncio
-async def test_confirmed_mount_launch_failure_is_reported_in_the_live_view() -> None:
-    async def start() -> None:
-        raise ValueError("Scan preparation failed")
+    async def start(verify: bool = True) -> None:
+        nonlocal seen_verify
+        seen_verify = verify

    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
    os.environ["ANTHROPIC_API_KEY"] = "test-key"
    loader._cached = None
    controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"mount_working_dir": True})
+    await controller.handle("setup.add_target", {"target": "https://example.com"})

-    with pytest.raises(ValueError, match="Scan preparation failed"):
-        await controller.handle("setup.confirm_mount", {"approved": True})
+    # A named target keeps the upfront model check.
+    await controller.handle("setup.start", {})

-    assert controller.scan_state == "failed"
-    assert controller.error == "Scan preparation failed"
+    assert seen_verify is True


@pytest.mark.asyncio
@@ -443,7 +376,7 @@ async def test_start_rejects_concurrent_and_repeated_submissions() -> None:
    entered = asyncio.Event()
    release = asyncio.Event()

-    async def start() -> None:
+    async def start(_verify: bool = True) -> None:
        entered.set()
        await release.wait()